Approximate explicit feature map for computational augmentation of RGB images of hematoxylin and eosin stained histopathological specimens (CROSBI ID 699883)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Kopriva, Ivica ; Sitnik, Dario ; Aralica, Gorana ; Paćić, Arijana ; Popović Hadžija, Marijana ; Hadžija, Mirko ;
engleski
Approximate explicit feature map for computational augmentation of RGB images of hematoxylin and eosin stained histopathological specimens
Hyperspectral imaging (HSI) is demonstrating the growing capability for disease diagnosis and surgical cancer resection. That is mainly due to high spectral resolution of HSI when compared with its color (RGB) counterparts. However, increased spectral resolution is often associated with the loss of spatial resolution. That combined with high cost hinders applicability of HSI. Herein, we propose computational approach that attempts to mimic the HSI. It is using an approximate explicit feature map (aEFM) to augment raw and/or stain normalized RGB images of the hematoxylin and eosin stained histopathological specimen. We demonstrate on two public labeled datasets, related to breast cancer and nuclei, the statistically significant improvement of performance of binary (caner vs. non-cancer) segmentation of augmented RGB images in comparison with the results achieved on their RGB counterparts. For the breast cancer, balanced accuracy is increased from 76.56%+/-9.05% to 80.42%+/-9.23% and F1 score from 13.34%+/-6.46% to 17.33%+/-6.36%. For nuclei, balanced accuracy is increased from 68.68%+/-9.25% to 79.99%+/-8.77% and F1 score from 46.92%+/-15.10% to 63.31%+/-14.50%. While constrained nonnegative matrix factorization was used for binary segmentation herein, we conjecture that aEFM based augmentation of RGB images can improve performance of more sophisticated segmentation methods such as deep networks.
hyperspectral microscopic image ; RGB microscopic image ; explicit feature map ; computational augmentation ; segmentation ; histopathology
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
1160301
2021.
objavljeno
10.1117/12.2579408
Podaci o matičnoj publikaciji
Medical Imaging 2021: Digital Pathology, vol. 11603
Tomaszevski, John ; Ward, Aaron
Belingham: SPIE
978-151-064035-1
1605-7422
2140-9045
Podaci o skupu
SPIE Medical Imaging 2021
predavanje
15.02.2021-20.02.2021
San Diego (CA), Sjedinjene Američke Države